Hi Sonia,

Sorry I might not have the statistics on the provided two methods, perhaps as 
input
I could also provide another method: currently there is an eco-project 
dl-on-flink
that supports running DL frameworks on top of the Flink and it will handle the 
data
exchange between java and python processes, which would allows to user the 
native
model directly. 

Best,
Yun


[1] https://github.com/flink-extended/dl-on-flink




------------------------------------------------------------------
From:Sonia-Florina Horchidan <[email protected]>
Send Time:2022 Jan. 7 (Fri.) 17:23
To:[email protected] <[email protected]>
Subject:Serving Machine Learning models



Hello,

I recently started looking into serving Machine Learning models for streaming 
data in Flink. To give more context, that would involve training a model 
offline (using PyTorch or TensorFlow), and calling it from inside a Flink job 
to do online inference on newly arrived data. I have found multiple 
discussions, presentations, and tools that could achieve this, and it seems 
like the two alternatives would be: (1) wrap the pre-trained models in a HTTP 
service (such as PyTorch Serve [1]) and let Flink do async calls for model 
scoring, or (2) convert the models into a standardized format (e.g., ONNX [2]), 
pre-load the model in memory for every task manager (or use external storage if 
needed) and call it for each new data point. 
Both approaches come with a set of advantages and drawbacks and, as far as I 
understand, there is no "silver bullet", since one approach could be more 
suitable than the other based on the application requirements. However, I would 
be curious to know what would be the "recommended" methods for model serving 
(if any) and what approaches are currently adopted by the users in the wild.
[1] https://pytorch.org/serve/
[2] https://onnx.ai/
Best regards,
Sonia

 [Kth Logo]

Sonia-Florina Horchidan
PhD Student
KTH Royal Institute of Technology
Software and Computer Systems (SCS)
School of Electrical Engineering and Computer Science (EECS)
Mobil: +46769751562
[email protected], www.kth.se

Reply via email to